Automotive Accident Severity Prediction Using Machine Learning

Prediction of the automotive accident severity plays a very crucial role in the smart transportation system. The main motive behind our research is to find out the specific features which could affect the vehicle accident severity. In this paper, some of the classification models, specifically logistic regression, artificial neural network, decision tree, k-nearest neighbors and random forest, have been implemented for predicting the accident severity. All the models have been verified, and the experimental results prove that these classification models have attained considerable accuracy. The results of this research can be used in the smart transportation system to predict if the road accident will be slight, severe or fatal, in accordance with the top three features as predicted from the machine learning model.